• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.40-49
• /
• 2018

We propose a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. We propose detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). The feature vector is applied to LDA and using Euclidean distance of intra-class variance and inter class variance in the 2nd dimension, the final analysis and matching is performed. Experimental results show that the proposed method has a wider distribution when the input image is rotated $45^{\circ}$ left / right. We can improve the recognition rate by applying this feature value to a single algorithm and complex algorithm, and it is possible to recognize in real time because it does not require much calculation amount due to dimensional reduction.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.607-616
• /
• 2014

Face recognition is a big challenge in surveillance system since different rotation angles of the face make the difficulty to recognize the face of the same person. This paper proposes a novel method to recognize face with different head poses by using 3D information of the face. Firstly, head pose estimation (estimation of different head pose angles) is accomplished by the POSIT algorithm. Then, 3D face image data is constructed by using head pose estimation. After that, 2D image and the constructed 3D face matching is performed. Face verification is accomplished by using commercial face recognition SDK. Performance evaluation of the proposed method indicates that the error range of head pose estimation is below 10 degree and the matching rate is about 95%.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.43-50
• /
• 1997

In this paper, we present a method that can recognize face images by use of a sparse population code that is a learning model about a receptive fields of the simple cells in the primary visual cortex. Twenty front-view facial images form twenty persons were used for the training process, and 200 varied facial images, 20 per person, were used for test. The correct recognition rate was 100% for only the front-view test facial images, which include the images either with spectacles or of various expressions, while it was 90% in average for the total input images that include rotated faces. We analyzed the effect of nonlinear functon that determine the sparseness, and compared recognition rate using the sparese population code with that using eigenvectors (eigenfaces), which is compact code that makes contrast with the sparse population code.

• The Journal of Korea Robotics Society
• /
• v.5 no.2
• /
• pp.152-159
• /
• 2010

Finding a head of a person in a scene is very important for taking a well composed picture by a robot photographer because it depends on the position of the head. So in this paper, we propose a robust head tracking algorithm using a hybrid of an omega shape tracker and local binary pattern (LBP) AdaBoost face detector for the robot photographer to take a fine picture automatically. Face detection algorithms have good performance in terms of finding frontal faces, but it is not the same for rotated faces. In addition, when the face is occluded by a hat or hands, it has a hard time finding the face. In order to solve this problem, the omega shape tracker based on active shape model (ASM) is presented. The omega shape tracker is robust to occlusion and illuminationchange. However, whenthe environment is dynamic,such as when people move fast and when there is a complex background, its performance is unsatisfactory. Therefore, a method combining the face detection algorithm and the omega shape tracker by probabilistic method using histograms of oriented gradient (HOG) descriptor is proposed in this paper, in order to robustly find human head. A robot photographer was also implemented to abide by the 'rule of thirds' and to take photos when people smile.

• Journal of Korea Game Society
• /
• v.21 no.3
• /
• pp.13-24
• /
• 2021

This paper shows the face rotation applicable to game character facial illustration. Existing studies limited data to human face data, required a large amount of data, and the synthesized results were not good. In this paper, the following method was introduced to solve the existing problems of existing studies. First, a 3D model with features of the input image was rotated and then rendered as a 2D image to construct a data set. Second, by designing GAN that can learn features of various poses from the data built through the 3D model, the input image can be synthesized at a desired pose. This paper presents the results of synthesizing the game character face illustration. From the synthesized result, it can be confirmed that the proposed method works well.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.212-227
• /
• 2008

Since 3D face can be rotated freely in 3D space and illumination effects can be modeled properly, 3D face modeling Is more precise and realistic in face pose, illumination, and expression than 2D face modeling. Thus, 3D modeling is necessitated much in face recognition, game, avatar, and etc. In this paper, we propose a 3D face modeling method based on 3D morphable shape modeling. The proposed 3D modeling method first constructs a 3D morphable shape model out of 3D face scan data obtained using a 3D scanner Next, the proposed method extracts and matches feature points of the face from 2D image sequence containing a face to be modeled, and then estimates 3D vertex coordinates of the feature points using a factorization based SfM technique. Then, the proposed method obtains a 3D shape model of the face to be modeled by fitting the 3D vertices to the constructed 3D morphable shape model. Also, the proposed method makes a cylindrical texture map using 2D face image sequence. Finally, the proposed method builds a 3D face model by rendering the 3D face shape model with the cylindrical texture map. Through building processes of 3D face model by the proposed method, it is shown that the proposed method is relatively easy, fast and precise than the previous 3D face model methods.

• The korean journal of orthodontics
• /
• v.26 no.2 s.55
• /
• pp.219-232
• /
• 1996

The purpose of this study was to evaluate treatment effects of bionator in Class II division 1 malocclusion by FEM(Finite Element Method). The 73 subjects were classified into good result group and poor result group in reference to posttreatment molar relation, posttreatment overbite and overjet, posttreatment profile, and relapse. Pretreatment and posttreatment lateral cephalograms were taken and FEM was performed. The results were as follow; 1. There was no statistical significance in treatment changes between the sexes, and between the treatment result groups. 2. Treatment changes were not significantly different among the age groups. 3. The effect of treatment period groups on skeletal and dentoalveolar changes were analyzed using ANOVA. Body of maxilla, upper incisor, anterior face, ramus, upper anterior face, lower anterior face and treatment effect were correlated with the treatment period, but correlation coefficients were low. 4. The results of present investigation confirm that Class II bionator can assist in the correction of Class II division 1 malocclusion, mainly due to dentoalveolar changes. 5. There is significant difference in skeletal and dentoalveolar pattern between good result group and poor result group. In poor result group, maxilla was relatively downward and backward rotated, mandible was relatively backward rotated, upper incisor was in relatively lingual position, lower incisor was in relatively labial position.

• The korean journal of orthodontics
• /
• v.17 no.2
• /
• pp.185-200
• /
• 1987

This paper was undertaken to observe the displacement of craniofacial complex with cervical headgear and to compare narrowing or widening effect of palate by use of contraction or expansion face-bow, respectively. The 3-dimensional finite element method(FEM) was used for a mathematical model composed of 597 nodes and 790 elements and an electrical resistance strain gauge investigation was performed to validate the finite element model. The outer bow of cervical headgear was adjusted to be placed below the occlusal plane by $25^{\circ}$ and met the midsagittal plane by $40^{\circ}$, and was loaded 1kg on each right and left hook toward posterior direction. The results were as follows 1. Generally, the maxillary teeth and facial bone were displaced in posterior, medial and downward direction. 2. It was the maxillary 2nd bicuspid that moved bodily. 3. The craniofacial complex rotated in a clockwise direction around the rotating axis which lay from the most posterior and lowest point connecting nasal crest of maxillary bone and vomer, progressively toward a more posterior, lateral and upward direction, anterior and upper area of pterygomaxillary fissure, base of medial pterygoid plate and laterally to the contact area of zygomatic arch with squamous part of temporal bone. 4. No contraction effect was observed by contraction face-bow when compared to the standard face-bow. 5. In case of expansion face-bow, the areas of maxillary 2nd bicuspid, molars and palate were expanded remarkably.

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.3
• /
• pp.311-317
• /
• 2015

Phenotypic characterization and body biometric in 13 traits (height at withers, body length, chest girth, paunch girth, ear length, tail length, length of tail up to switch, face length, face width, horn length, circumference of horn at base, distances between pin bone and hip bone) were recorded in 233 adult Gojri buffaloes from Punjab and Himachal Pradesh states of India. Traits were analysed by using varimax rotated principal component analysis (PCA) with Kaiser Normalization to explain body conformation. PCA revealed four components which explained about 70.9% of the total variation. First component described the general body conformation and explained 31.5% of total variation. It was represented by significant positive high loading of height at wither, body length, heart girth, face length and face width. The communality ranged from 0.83 (hip bone distance) to 0.45 (horn length) and unique factors ranged from 0.16 to 0.55 for all these 13 different biometric traits. Present study suggests that first principal component can be used in the evaluation and comparison of body conformation in buffaloes and thus provides an opportunity to distinguish between early and late maturing to adult, based on a small group of biometric traits to explain body conformation in adult buffaloes.

• Archives of Plastic Surgery
• /
• v.45 no.6
• /
• pp.572-577
• /
• 2018

Background Mandibular contouring surgery to produce a more slender and small face has become popular, especially in East Asia. Narrowing genioplasty should be simultaneously performed with mandibular angle resection to achieve satisfactory results. In Korea, T-genioplasty has been frequently performed for chin narrowing. The authors developed a new, safe, and reliable method, termed M-genioplasty, that can provide a more slender and attractive lower face. Methods From June 2013 to December 2017, 36 patients underwent M-genioplasty with mandibular angle resection for lower facial contouring. Horizontal and vertical osteotomies were performed obliquely. The resected bone segments were wedge-shaped. The remaining two bone segments were rotated and approximated centrally. The lateral mandible bony step-off was trimmed off for mandibular angle resection. Results In all patients, the facial contour sufficiently improved, and most patients were satisfied with the outcome. No severe complications took place during postoperative follow-up. Conclusions M-genioplasty can provide more mandibular angle resection and can create a more acute chin angle without bone resorption than other methods, including T-genioplasty. M-genioplasty with mandibular angle resection is a safer, more accurate, and more reliable method for lower facial contouring.